AMD Bulldozer Kernel Patch Trying out the "x86, AMD: Correct F15h IC aliasing issue" patch by AMD's Borislav Petkov from a Linux 3.1 (post RC10, Git) and testing with the unalias_va_addr=(32|64|off) options.
HTML result view exported from: https://openbenchmarking.org/result/1110200-AR-BULLDOZER41&sro .
AMD Bulldozer Kernel Patch Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Linux 3.0 Linux 3.1 - unalias_va_addr=off Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores) ASUS Crosshair V Formula ATI RD890 PCI to PCI bridge 8192MB 60GB OCZ VERTEX2 NVIDIA GeForce GTX 460 768MB (675/1800MHz) Realtek ALC889 Intel 82583V Gigabit Connection Ubuntu 11.10 3.0.0-12-generic (x86_64) Unity 4.22.0 X Server 1.10.4 NVIDIA 285.05.09 4.2.0 NVIDIA 285.05.09 GCC 4.6.1 ext4 1920x1080 3.1.0-rc10-ic-aliasing-patch+ (x86_64) OpenBenchmarking.org System Details - Compiz was running on this system.
AMD Bulldozer Kernel Patch c-ray: Total Time smallpt: Global Illumination Renderer; 100 Samples povray: Total Time tscp: AI Chess Performance graphics-magick: HWB Color Space graphics-magick: Blur graphics-magick: Local Adaptive Thresholding graphics-magick: Resizing graphics-magick: Sharpen john-the-ripper: Traditional DES john-the-ripper: MD5 john-the-ripper: Blowfish openssl: RSA 4096-bit Performance compress-7zip: Compress Speed Test encode-mp3: WAV To MP3 encode-flac: WAV To FLAC ffmpeg: AVI To NTSC VCD x264: H.264 Video Encoding mafft: Multiple Sequence Alignment npb: BT.A npb: CG.B npb: EP.B npb: FT.B npb: IS.C npb: LU.A npb: MG.B npb: SP.A npb: UA.A clomp: Static OMP Speedup openarena: 1920 x 1080 nexuiz: 1920 x 1080 - No - Off lightsmark: 1920 x 1080 Linux 3.0 Linux 3.1 - unalias_va_addr=off Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 51.06 103 823 314874 165 99 68 133 65 3678333 15490 1002 68.75 17753 27.02 7.85 10.10 102.23 26.65 11240.21 2803.63 164.60 6593.08 108.11 11693.80 4484.59 5495.79 38.70 2.44 456.10 174.74 500.83 51.09 104 813 314158 165 99 68 132 65 3685667 15529 1002 69.05 18076 27.03 7.84 10.04 101.97 26.65 11220.98 2787.86 164.60 6559.76 108.15 11566.86 4376.58 5400.64 38.60 2.46 455.20 174.32 500.86 51.34 104 818 314299 165 99 68 133 65 3646667 15525 1001 68.53 17963 27.05 7.84 10.05 102.25 26.63 11208.12 2815.10 162.66 6573.27 107.81 11702.03 4460.53 5455.78 38.56 2.46 463.90 174.41 500.63 51.07 103 819 314227 165 99 69 133 65 3664000 15383 1001 68.83 17917 27.02 7.84 10.03 102.70 26.65 11242.57 2822.40 161.35 6563.26 108.14 11684.25 4473.16 5442.69 38.59 2.47 460.07 174.57 500.41 OpenBenchmarking.org
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 51.06 51.34 51.07 51.09
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 103 104 103 104
POV-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.6.1 Total Time Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 200 400 600 800 1000 823 818 819 813
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 70K 140K 210K 280K 350K SE +/- 104.96, N = 5 SE +/- 91.49, N = 5 SE +/- 199.57, N = 5 SE +/- 421.11, N = 5 314874 314299 314227 314158
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: HWB Color Space Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 165 165 165 165
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Blur Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 99 99 99 99
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 15 30 45 60 75 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 68 68 69 68
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 133 133 133 132
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 65 65 65 65
John The Ripper Test: Traditional DES OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: Traditional DES Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 800K 1600K 2400K 3200K 4000K SE +/- 29901.69, N = 3 SE +/- 2403.70, N = 3 SE +/- 15275.25, N = 3 SE +/- 9614.80, N = 3 3678333 3646667 3664000 3685667
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: MD5 Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 3K 6K 9K 12K 15K SE +/- 29.42, N = 3 SE +/- 4.91, N = 3 SE +/- 153.50, N = 3 SE +/- 4.04, N = 3 15490 15525 15383 15529
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.8 Test: Blowfish Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 200 400 600 800 1000 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 1002 1001 1001 1002
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.0a RSA 4096-bit Performance Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 15 30 45 60 75 SE +/- 0.22, N = 4 SE +/- 0.31, N = 4 SE +/- 0.27, N = 4 SE +/- 0.03, N = 4 68.75 68.53 68.83 69.05
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 9.13 Compress Speed Test Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 4K 8K 12K 16K 20K SE +/- 169.50, N = 3 SE +/- 81.72, N = 3 SE +/- 79.64, N = 3 SE +/- 22.21, N = 3 17753 17963 17917 18076
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.98.2 WAV To MP3 Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 6 12 18 24 30 SE +/- 0.00, N = 5 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 27.02 27.05 27.02 27.03
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.2.1 WAV To FLAC Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 2 4 6 8 10 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 7.85 7.84 7.84 7.84
FFmpeg AVI To NTSC VCD OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 0.8.2 AVI To NTSC VCD Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 10.10 10.05 10.03 10.04
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2010-11-22 H.264 Video Encoding Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 20 40 60 80 100 SE +/- 0.52, N = 3 SE +/- 0.69, N = 3 SE +/- 0.43, N = 3 SE +/- 0.59, N = 3 102.23 102.25 102.70 101.97
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.706 Multiple Sequence Alignment Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 26.65 26.63 26.65 26.65
NAS Parallel Benchmarks Test / Class: BT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: BT.A Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 2K 4K 6K 8K 10K SE +/- 15.70, N = 3 SE +/- 11.62, N = 3 SE +/- 7.65, N = 3 SE +/- 14.43, N = 3 11240.21 11208.12 11242.57 11220.98
NAS Parallel Benchmarks Test / Class: CG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: CG.B Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 600 1200 1800 2400 3000 SE +/- 0.14, N = 3 SE +/- 2.49, N = 3 SE +/- 1.31, N = 3 SE +/- 10.41, N = 3 2803.63 2815.10 2822.40 2787.86
NAS Parallel Benchmarks Test / Class: EP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: EP.B Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 40 80 120 160 200 SE +/- 0.25, N = 3 SE +/- 0.60, N = 3 SE +/- 0.83, N = 3 SE +/- 0.15, N = 3 164.60 162.66 161.35 164.60
NAS Parallel Benchmarks Test / Class: FT.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: FT.B Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 1400 2800 4200 5600 7000 SE +/- 51.39, N = 3 SE +/- 36.57, N = 3 SE +/- 37.81, N = 3 SE +/- 43.93, N = 3 6593.08 6573.27 6563.26 6559.76
NAS Parallel Benchmarks Test / Class: IS.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: IS.C Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 108.11 107.81 108.14 108.15
NAS Parallel Benchmarks Test / Class: LU.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.A Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 3K 6K 9K 12K 15K SE +/- 13.20, N = 3 SE +/- 30.06, N = 3 SE +/- 24.97, N = 3 SE +/- 24.67, N = 3 11693.80 11702.03 11684.25 11566.86
NAS Parallel Benchmarks Test / Class: MG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: MG.B Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 1000 2000 3000 4000 5000 SE +/- 8.50, N = 3 SE +/- 4.36, N = 3 SE +/- 3.74, N = 3 SE +/- 1.24, N = 3 4484.59 4460.53 4473.16 4376.58
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: SP.A Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 1200 2400 3600 4800 6000 SE +/- 46.23, N = 3 SE +/- 82.57, N = 3 SE +/- 58.11, N = 3 SE +/- 80.52, N = 3 5495.79 5455.78 5442.69 5400.64
NAS Parallel Benchmarks Test / Class: UA.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: UA.A Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.17, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 38.70 38.56 38.59 38.60
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 0.5558 1.1116 1.6674 2.2232 2.779 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.03, N = 5 SE +/- 0.03, N = 5 2.44 2.46 2.47 2.46
OpenArena Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better OpenArena 0.8.5 Resolution: 1920 x 1080 Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 100 200 300 400 500 SE +/- 1.76, N = 3 SE +/- 4.33, N = 3 SE +/- 2.18, N = 3 SE +/- 0.90, N = 3 456.10 463.90 460.07 455.20
Nexuiz Resolution: 1920 x 1080 - HDR: No - Sound: Off OpenBenchmarking.org Frames Per Second, More Is Better Nexuiz 2.5.2 Resolution: 1920 x 1080 - HDR: No - Sound: Off Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 0.19, N = 3 SE +/- 0.22, N = 3 SE +/- 0.38, N = 3 174.74 174.41 174.57 174.32
Lightsmark Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better Lightsmark 2008 Resolution: 1920 x 1080 Linux 3.0 Linux 3.1 - unalias_va_addr Linux 3.1 - unalias_va_addr=64 Linux 3.1 - unalias_va_addr=off 110 220 330 440 550 SE +/- 0.21, N = 3 SE +/- 0.23, N = 3 SE +/- 0.37, N = 3 SE +/- 0.42, N = 3 500.83 500.63 500.41 500.86
Phoronix Test Suite v10.8.5